def test_cp_dir(self):
fs.rm("/tmp/labm8")
fs.rm("/tmp/labm8.copy")
fs.mkdir("/tmp/labm8/foo/bar")
self._test(False, fs.exists("/tmp/labm8.copy"))
fs.cp("/tmp/labm8/", "/tmp/labm8.copy")
self._test(True, fs.isdir("/tmp/labm8.copy"))
self._test(True, fs.isdir("/tmp/labm8.copy/foo"))
self._test(True, fs.isdir("/tmp/labm8.copy/foo/bar"))
def test_cp_over_dir(self):
fs.mkdir("/tmp/labm8.tmp.src")
system.echo("Hello, world!", "/tmp/labm8.tmp.src/foo")
fs.rm("/tmp/labm8.tmp.copy")
fs.mkdir("/tmp/labm8.tmp.copy")
self._test(True, fs.isdir("/tmp/labm8.tmp.src"))
self._test(True, fs.isfile("/tmp/labm8.tmp.src/foo"))
self._test(True, fs.isdir("/tmp/labm8.tmp.copy"))
self._test(False, fs.isfile("/tmp/labm8.tmp.copy/foo"))
fs.cp("/tmp/labm8.tmp.src", "/tmp/labm8.tmp.copy/")
self._test(True, fs.isdir("/tmp/labm8.tmp.src"))
self._test(True, fs.isfile("/tmp/labm8.tmp.src/foo"))
self._test(True, fs.isdir("/tmp/labm8.tmp.copy"))
self._test(True, fs.isfile("/tmp/labm8.tmp.copy/foo"))
self._test(fs.read("/tmp/labm8.tmp.src/foo"),
fs.read("/tmp/labm8.tmp.copy/foo"))
def __init__(self, *args, **kwargs):
"""
Construct a SkelCL server.
"""
# Fail if we can't find the path
if not fs.isdir(self.LLVM_PATH):
io.fatal("Could not find llvm path '{0}'".format(self.LLVM_PATH))
super(Server, self).__init__(*args, **kwargs)
io.info("Registered server %s/SkelCLServer ..." % SESSION_NAME)
# Setup persistent database.
self.db = migrate(Database())
self.db.status_report()
# Create an in-memory sample strategy cache.
self.strategies = cache.TransientCache()
def test_mkopen(self):
fs.rm("/tmp/labm8.dir")
self._test(False, fs.isdir("/tmp/labm8.dir/"))
f = fs.mkopen("/tmp/labm8.dir/foo", "w")
self._test(True, fs.isdir("/tmp/labm8.dir/"))
f.close()
def test_mkdir_exists(self):
fs.mkdir("/tmp/labm8.dir/")
self._test(True, fs.isdir("/tmp/labm8.dir/"))
fs.mkdir("/tmp/labm8.dir/")
fs.mkdir("/tmp/labm8.dir/")
self._test(True, fs.isdir("/tmp/labm8.dir/"))
def test_mkdir_parents(self):
self._test(False, fs.isdir("/tmp/labm8.dir/foo/bar"))
fs.mkdir("/tmp/labm8.dir/foo/bar")
self._test(True, fs.isdir("/tmp/labm8.dir/foo/bar"))
def test_mkdir(self):
fs.rm("/tmp/labm8.dir")
self._test(False, fs.isdir("/tmp/labm8.dir"))
fs.mkdir("/tmp/labm8.dir")
self._test(True, fs.isdir("/tmp/labm8.dir"))
def test_isdir(self):
self._test(False, fs.isdir(__file__))
self._test(True, fs.isdir("/"))
self._test(False, fs.isdir("/not/a/real/path (I hope!)"))
def test_init_and_empty(self):
c = cache.Cache("__test__")
self.assertTrue(fs.isdir(fs.path(cache.ROOT, "__test__")))
c.empty()
self.assertFalse(fs.isdir(fs.path(cache.ROOT, "__test__")))
def test_mkdir_exists():
fs.mkdir("/tmp/labm8.dir/")
assert fs.isdir("/tmp/labm8.dir/")
fs.mkdir("/tmp/labm8.dir/")
fs.mkdir("/tmp/labm8.dir/")
assert fs.isdir("/tmp/labm8.dir/")
def test_mkdir_parents():
assert not fs.isdir("/tmp/labm8.dir/foo/bar")
fs.mkdir("/tmp/labm8.dir/foo/bar")
assert fs.isdir("/tmp/labm8.dir/foo/bar")
def test_mkdir():
fs.rm("/tmp/labm8.dir")
assert not fs.isdir("/tmp/labm8.dir")
fs.mkdir("/tmp/labm8.dir")
assert fs.isdir("/tmp/labm8.dir")
def test_isdir():
assert not fs.isdir(__file__)
assert fs.isdir("/")
assert not fs.isdir("/not/a/real/path (I hope!)")
def test_init_and_empty(self):
c = cache.FSCache("/tmp/labm8-cache-init-and-empty")
self.assertTrue(fs.isdir("/tmp/labm8-cache-init-and-empty"))
c.clear()
self.assertFalse(fs.isdir("/tmp/labm8-cache-init-and-empty"))
def _locked_train(self) -> 'Model':
tf = self._init_tensorflow(infer=False)
# training options
learning_rate = self.train_opts["learning_rate"]
decay_rate = self.train_opts["lr_decay_rate"]
# resume from prior checkpoint
ckpt_path, ckpt_paths = None, None
if self.checkpoint_path:
# check that all necessary files exist
assert(fs.isdir(self.checkpoint_path))
ckpt = tf.train.get_checkpoint_state(self.checkpoint_path)
assert(ckpt)
assert(ckpt.model_checkpoint_path)
ckpt_path, ckpt_paths = self._get_params_path(ckpt)
with tf.Session() as sess:
tf.global_variables_initializer().run()
# keep all checkpoints
saver = tf.train.Saver(tf.global_variables(), max_to_keep=100)
# restore model from closest checkpoint
if ckpt_path:
log.debug("restoring", ckpt_path)
saver.restore(sess, ckpt_path)
log.verbose("restored checkpoint {}".format(ckpt_path))
# make sure we don't lose track of other checkpoints
if ckpt_paths:
saver.recover_last_checkpoints(ckpt_paths)
coord = tf.train.Coordinator()
self.corpus.create_batches()
threading.Thread(target=self.enqueue_x, args=(coord, sess)).start()
max_batch = self.epochs * self.corpus.num_batches
# progress bar
bar = progressbar.ProgressBar(max_value=max_batch)
if sess.run(self.epoch) != self.epochs:
log.info("training", self)
for e in range(sess.run(self.epoch) + 1, self.epochs + 1):
epoch_start = time()
# decay and set learning rate
new_learning_rate = learning_rate * (
(float(100 - decay_rate) / 100.0) ** (e - 1))
sess.run(tf.assign(self.learning_rate, new_learning_rate))
sess.run(tf.assign(self.epoch, e))
for b in range(self.corpus.num_batches):
train_cost, _, state, _ = sess.run([self.cost, self.KL_cost, self.final_state, self.train_op])
# update progress bar
batch_num = (e - 1) * self.corpus.num_batches + b
bar.update(batch_num)
save = self.opts["train_opts"]["intermediate_checkpoints"]
save |= e == self.epochs # always save on last epoch
if save:
saver.save(sess, self.cache.keypath("model.ckpt"),
global_step=batch_num)
next_checkpoint = e * self.corpus.num_batches + b
max_epoch = self.epochs
log.verbose("\n{self} epoch {e} / {max_epoch}. "
"next checkpoint at batch {next_checkpoint}"
.format(**vars()))
# update training time
epoch_duration = time() - epoch_start
self.stats["epoch_costs"].append(float(train_cost))
self.stats["epoch_times"].append(epoch_duration)
self.stats["epoch_batches"].append(batch_num + 1)
self._flush_meta()
coord.request_stop()
return self
#!/usr/bin/env python3.6
import sys
from progressbar import ProgressBar
from labm8 import crypto
from labm8 import fs
if __name__ == "__main__":
inpath = sys.argv[1]
outdir = sys.argv[2]
print(f"reading from {inpath} into {outdir}")
assert fs.isfile(inpath)
assert not fs.exists(outdir) or fs.isdir(outdir)
fs.mkdir(outdir)
with open(inpath) as infile:
text = infile.read()
kernels = text.split("// ==== START SAMPLE ====")
kernels = [kernel.strip() for kernel in kernels if kernel.strip()]
print(len(kernels), "kernels")
sha1s = [crypto.sha1_str(kernel) for kernel in kernels]
for kernel, sha1 in ProgressBar()(list(zip(kernels, sha1s))):
with open(f"{outdir}/{sha1}.txt", "w") as outfile:
print(kernel, file=outfile)
def test_mkopen():
fs.rm("/tmp/labm8.dir")
assert not fs.isdir("/tmp/labm8.dir/")
f = fs.mkopen("/tmp/labm8.dir/foo", "w")
assert fs.isdir("/tmp/labm8.dir/")
f.close()
def __init__(self, contentid: str, path: str = None, **opts):
"""
Instantiate a corpus.
If this is a new corpus, a number of files will be created, which may
take some time.
Arguments:
contentid (str): ID of corpus content.
path (str, optional): Path to corpus.
**opts: Keyword options.
"""
def _init_error(err: Exception) -> None:
""" tidy up in case of error """
log.error("corpus creation failed. Deleting corpus files")
paths = [
fs.path(self.contentcache.path, "kernels.db"),
fs.path(self.cache.path, "corpus.txt"),
fs.path(self.cache.path, "tensor.npy"),
fs.path(self.cache.path, "atomizer.pkl")
]
for path in paths:
if fs.exists(path):
log.info("removing", path)
fs.rm(path)
raise err
# Validate options
for key in opts.keys():
if key not in DEFAULT_CORPUS_OPTS:
raise clgen.UserError(
"Unsupported corpus option '{}'. Valid keys: {}".format(
key, ','.join(sorted(DEFAULT_CORPUS_OPTS.keys()))))
self.opts = deepcopy(DEFAULT_CORPUS_OPTS)
clgen.update(self.opts, opts)
self.contentid = contentid
self.hash = self._hash(contentid, self.opts)
self.cache = Cache(fs.path("corpus", self.hash))
self.contentcache = Cache(fs.path("contentfiles", contentid))
self.kernels_db = self.contentcache['kernels.db']
log.debug("corpus {hash}".format(hash=self.hash))
try:
if path is not None:
if not fs.isdir(path):
raise clgen.UserError(
"Corpus path '{}' is not a directory".format(path))
# create kernels database if necessary
if not self.contentcache["kernels.db"]:
self._create_kernels_db(path, self.opts["encoding"])
assert (self.contentcache["kernels.db"])
# create corpus text if not exists
if not self.cache["corpus.txt"]:
self._create_txt()
assert (self.cache["corpus.txt"])
# create atomizer if needed
if self.cache["atomizer.pkl"]:
self._load_atomizer()
assert (self.cache["atomizer.pkl"])
else:
self._create_atomizer(self.opts["vocabulary"])
except Exception as e:
_init_error(e)
def train(self, quiet: bool = False) -> None:
"""
Train model.
"""
tf = self._init_tensorflow(infer=False)
# training options
learning_rate = self.train_opts["learning_rate"]
decay_rate = self.train_opts["lr_decary_rate"]
checkpoint_path = fs.path(self.cache.path, "model.ckpt")
# resume from prior checkpoint
ckpt_path, ckpt_paths = None, None
if self.checkpoint_path:
# check if all necessary files exist
assert (fs.isdir(self.checkpoint_path))
ckpt = tf.train.get_checkpoint_state(self.checkpoint_path)
assert (ckpt)
assert (ckpt.model_checkpoint_path)
ckpt_path, ckpt_paths = self._get_params_path(ckpt)
with tf.Session() as sess:
tf.global_variables_initializer().run()
# keep all checkpoints
saver = tf.train.Saver(tf.global_variables(), max_to_keep=100)
# restore model from closest checkpoint
if ckpt_path:
log.debug("restoring", ckpt_path)
saver.restore(sess, ckpt_path)
log.info("restored checkpoint {}".format(ckpt_path))
# make sure we don't lose track of other checkpoints
if ckpt_paths:
saver.recover_last_checkpoints(ckpt_paths)
start_batch = sess.run(self.epoch) * self.corpus.num_batches
batch_count = 0
total_elapsed = 0
total_atomize = 0
total_checkpoint, avg_checkpoint = 0, 0
eta_d, eta_h, eta_m = 0, 0, 0
for e in range(sess.run(self.epoch) + 1, self.epochs + 1):
if quiet:
log.info("epoch", e, "of", self.epochs + 1)
# decay and set learning rate
new_learning_rate = learning_rate * (
(float(100 - decay_rate) / 100.0)**(e - 1))
sess.run(tf.assign(self.learning_rate, new_learning_rate))
sess.run(tf.assign(self.epoch, e))
time_start = time.time()
self.corpus.create_batches()
total_atomize += time.time() - time_start
avg_atomize = total_atomize / e
state = sess.run(self.initial_state)
for b in range(self.corpus.num_batches):
time_start = time.time()
batch_count += 1
x, y = self.corpus.next_batch()
feed = {self.input_data: x, self.targets: y}
for i, (c, h) in enumerate(self.initial_state):
feed[c] = state[i].c
feed[h] = state[i].h
train_loss, state, _ = sess.run(
[self.cost, self.final_state, self.train_op], feed)
batch_num = (e - 1) * self.corpus.num_batches + b
max_batch = self.epochs * self.corpus.num_batches
progress = float((batch_num + 1 - start_batch) /
(max_batch - start_batch))
time_end = time.time()
elapsed = time_end - time_start
if not quiet:
total_elapsed += elapsed
avg_elapsed = total_elapsed / batch_count
remaining_time = (
(max_batch - batch_count) * avg_elapsed
+ # batches
(e - self.epochs) * avg_atomize + # atomizings
(e - self.epochs) * avg_checkpoint) # checkpoints
eta_h, eta_m = divmod(remaining_time / 60, 60)
eta_d, eta_h = divmod(eta_h, 24)
print("\r\033[K"
"{progress:3.1f}% | "
"{size}x{layers}x{max_epoch} {model} | "
"epoch={epoch_num}/{max_epoch} | "
"batch={batch_num}/{max_batch} | "
"lr={lr:.5f} | "
"loss={tloss:.3f} | "
"t1={time_atomize:.3f}s "
"t2={time_batch:.3f}s "
"t3={time_checkpoint:.3f}s | "
"eta={eta_d}d{eta_h}h{eta_m:02d}m".format(
size=self.rnn_size,
layers=self.num_layers,
model=self.model_type.upper(),
progress=progress * 100,
epoch_num=e,
max_epoch=self.epochs,
batch_num=b + 1,
max_batch=self.corpus.num_batches,
lr=new_learning_rate,
tloss=train_loss,
time_atomize=avg_atomize,
time_batch=avg_elapsed,
time_checkpoint=avg_checkpoint,
eta_d=int(eta_d),
eta_h=int(eta_h),
eta_m=int(eta_m)),
end="")
save = self.opts["train_opts"]["intermediate_checkpoints"]
save |= e == self.epochs # last epoch
if save:
if not quiet:
print()
time_start = time.time()
saver.save(sess, checkpoint_path, global_step=batch_num)
total_checkpoint += time.time() - time_start
avg_checkpoint = total_checkpoint / e
log.info("model saved to {}".format(checkpoint_path))
def __init__(self, contentid: str, path: str = None, **opts):
"""
Instantiate a corpus.
If this is a new corpus, a number of files will be created, which may
take some time.
Parameters
----------
contentid : str
ID of corpus content.
path : str, optional
Path to corpus.
**opts
Keyword options.
"""
# Validate options
for key in opts.keys():
if key not in DEFAULT_CORPUS_OPTS:
raise clgen.UserError(
"Unsupported corpus option '{}'. Valid keys: {}".format(
key, ','.join(sorted(DEFAULT_CORPUS_OPTS.keys()))))
self.opts = deepcopy(DEFAULT_CORPUS_OPTS)
types.update(self.opts, opts)
self.opts["id"] = contentid
# check that contentid exists
self.language = clgen.Language.from_str(opts.get("language"))
if (path is None and not fs.isdir(
clgen.cachepath("contentfiles",
f"{self.language}-{contentid}"))):
raise clgen.UserError(
"corpus {self.language}-{contentid} not found".format(
**vars()))
self.contentid = contentid
self.contentcache = clgen.mkcache("contentfiles",
f"{self.language}-{contentid}")
self.kernels_db = self.contentcache.keypath('kernels.db')
self.hash = self._hash(contentid, self.opts)
self.cache = clgen.mkcache("corpus", f"{self.language}-{self.hash}")
log.debug("contentfiles {self.contentid}".format(**vars()))
log.debug("corpus {hash}".format(hash=self.hash))
# validate metadata against cache
self.stats = {"preprocess_time": 0}
meta = deepcopy(self.to_json())
if self.cache.get("META"):
cached_meta = jsonutil.read_file(self.cache["META"])
self.stats = cached_meta["stats"] # restore stats
if "created" in cached_meta:
del cached_meta["created"]
del meta["created"]
if "stats" in cached_meta:
del cached_meta["stats"]
del meta["stats"]
if meta != cached_meta:
raise clgen.InternalError("corpus metadata mismatch")
else:
self._flush_meta()
with self.lock.acquire(replace_stale=True):
self._create_files(path)
